© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109499
    Prev
    Next
    INDEX
    Explanations

    criminal/legal issues

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens formatted as floating-point values (e.g. “0.69921875”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gift
    -0.07
     Paint
    -0.07
    .round
    -0.06
    Strong
    -0.06
     Train
    -0.06
    または
    -0.06
    [block
    -0.06
     shred
    -0.06
     पहल
    -0.06
     Byrne
    -0.06
    POSITIVE LOGITS
    erdale
    0.06
     دقی
    0.06
    comes
    0.06
    \data
    0.06
     Ticket
    0.06
    }};↵
    0.06
    _FUNCTIONS
    0.06
    вропей
    0.06
     Moines
    0.06
     demean
    0.06
    Activations Density 0.220%

    No Known Activations